INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Recomm

-0.73

ems

-0.69

mers

-0.69

ZI

-0.68

icable

-0.68

VERTISEMENT

-0.67

 Slay

-0.67

 Insect

-0.66

asury

-0.65

XP

-0.65

POSITIVE LOGITS

 Adin

0.74

acerb

0.68

 Uriel

0.68

emort

0.65

itia

0.65

ãĥ¯ãĥ³

0.64

enegger

0.64

picking

0.63

rition

0.62

 crem

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.